mlsanityData to 7 Oct 2026

What can Neural Referential Form Selectors Learn?

arXiv 2108.06806 ↗First posted 15 Aug 2021cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Despite achieving encouraging results, neural Referring Expression Generation models are often thought to lack transparency. We probed neural Referential Form Selection (RFS) models to find out to what extent the linguistic features influencing the RE form are learnt and captured by state-of-the-art RFS models. The results of 8 probing tasks show that all the defined features were learnt to some extent. The probing tasks pertaining to referential status and syntactic position exhibited the highest performance. The lowest performance was achieved by the probing models designed to predict discourse structure properties beyond the sentence level.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 12 of its 48 references that are in the map. First posted on arXiv 15 Aug 2021.

Builds on

12 of 48 references.

References · 12

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  5. 2019Designing and Interpreting Probes with Control Taskscited by 608
  6. 2017What do Neural Machine Translation Models Learn about Morphology?cited by 165
  7. 2018Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Informationcited by 97
  8. 2019Neural data-to-text generation: A comparison between pipeline and end-to-end architecturescited by 51
  9. 2020Probing Linguistic Features of Sentence-Level Representations in Neural Relation Extractioncited by 18
  10. 2021Probing for Bridging Inference in Transformer Language Modelscited by 14
  11. 2018NeuralREG: An end-to-end approach to referring expression generationcited by 7
  12. 2019Referring Expression Generation Using Entity Profilescited by 6

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1.

4 papers.

  1. 2022Non-neural Models Matter: A Re-evaluation of Neural Referring Expression Generation Systemscited by 7
  2. 2023Models of reference production: How do they withstand the test of time?cited by 2
  3. 2022The Role of Explanatory Value in Natural Language Processingcited by 0
  4. 2022Assessing Neural Referential Form Selectors on a Realistic Multilingual Datasetcited by 0